03-11-2013 11:46 AM
I have a time series containg data over a stretch of 52 weeks. My goal is the following : to smooth with an equallly weighted moving average the observations were no promotion (kinda looking for outliers) is present in order to use this new series for model setup and forecasting. Does proc expand provide with such an option? cause if i am not mistaken i have to use the whole series as an input or maybe i havent crasped the concept of proc expand in its whole.
03-11-2013 11:53 AM
I'm not fully sure what you're after, but most proc's in SAS allow a WHERE clause so you can specify what data the procedure uses.
Then you can recombine your data after you have a smoothed dataset.
03-11-2013 02:54 PM
I will give it a try, but I'm pretty sure I'm missing the mark - in this example I'm using EXPAND to "smooth a pattern" with a moving average window of 5 observations:
proc expand data=sashelp.air out=out method=none;
convert air=predict / transformout=(movave 5);
set sashelp.air out;
proc sgplot data=out;
series x=date y=air;
series x=date y=predict;
It would be very helpful if you could an example (how does the data look like now? How would you like the results to look like?).